© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 107207
    Prev
    Next
    INDEX
    Explanations

    connections between actions and positive outcomes, particularly in a financial or resource-saving context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦↵
    -0.07
    -packages
    -0.07
     (~
    -0.07
    éĪ
    -0.06
     localVar
    -0.06
     Mart
    -0.06
     Brill
    -0.06
    -Mart
    -0.06
     worst
    -0.06
     vest
    -0.06
    POSITIVE LOGITS
     ultimately
    0.13
     Ultimately
    0.11
    Ultimately
    0.09
     indirectly
    0.08
     ultimate
    0.08
     overall
    0.08
     곧
    0.08
     hopefully
    0.07
    ult
    0.07
     eventually
    0.07
    Activations Density 0.031%

    No Known Activations